Improving Dual-Encoder Training through Dynamic Indexes for Negative MiningDownload PDFOpen Website

Published: 01 Jan 2023, Last Modified: 20 Jun 2023AISTATS 2023Readers: Everyone
Abstract: Dual encoder models are ubiquitous in modern classification and retrieval. Crucial for training such dual encoders is an accurate estimation of gradients from the partition function of the softmax ...
0 Replies

Loading